Language Processing for Speech Understanding.

Abstract

This report considers language understanding techniques and control strategies that can be applied to provide higher-level support to aid in the understanding of spoken utterances. The discussion is illustrated with concepts and examples from the BBN speech understanding system, HWIM (Hear What I Mean). The HWIM system was conceived as an assistant to a travel budget manager, a system that would store information about planned and taken trips, travel budgets and their planning. The system was able to respond to commands and answer questions spoken into a microphone, and was able to synthesize spoken responses as output. HWIM was a prototype system used to drive speech understanding research. It used a phonetic-based approach, with no speaker training, a large vocabulary, and a relatively unconstraining English grammar. Discussed here is the control structure of the HWIM and the parsing algorithm used to parse sentences from the middle-out, using an ATN grammar.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 1983
Accession Number
ADA131281

Entities

People

  • W. A. Woods

Organizations

  • BBN Technologies

Tags

Communities of Interest

  • Ground and Sea Platforms
  • Materials and Manufacturing Processes
  • Space

DTIC Thesaurus Topics

  • Acoustic Signals
  • Algorithms
  • Artificial Intelligence
  • Automata
  • Automated Speech Recognition
  • Computational Science
  • Dictionaries
  • Grammars
  • Information Processing
  • Language
  • Linguistics
  • Military Research
  • Natural Languages
  • Recognition
  • Semantics
  • Specifications
  • Syntax

Readers

  • Computational Linguistics
  • Software Engineering
  • Speech Processing/Speech Recognition.